Files

T

Leonid PershinandCursor 07bb521b70 Add Assistent reference books and remove training dataset output.

Introduce books/ with civitai-krea2 and HF fictext builders, sha-diff seed to VM, and drop train.jsonl from the civitai scrape pipeline.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-23 22:56:07 +03:00

1.7 KiB

Raw Permalink Blame History

Assistent Knowledge Hub (swarm-assistent)

gpu-rent builds and seeds books locally. Runtime lives in swarm-assistent.

VM layout

/mnt/swarm_data/Assistent/books/<book-id>/
  book.yaml          # title, description, content_kind
  search.jsonl       # FTS rows (unified contract)
  meta.json          # row_count, content_sha, built_at
  .gpu-rent-meta.json  # same sha for gpu-rent skip/push

Unified search row

{
  "id": "civitai-krea2:42",
  "book": "civitai-krea2",
  "title": "",
  "tags": ["woman"],
  "text": "excerpt ≤500 chars",
  "body": "longer chunk",
  "rating": "pg13",
  "meta": {}
}

swarm-assistent tasks (not in gpu-rent)

Knowledge/IKnowledgeSource.cs + adapters: Book, MemorySeed, MemoryPersonal, Tag, Session
AssistentKnowledgeHub: ListCatalog, Search, Upsert, Forget, RunPipeline, BuildSystemLayer
Remove training UI: Обучение tab, AssistentTrainingJobs, AssistentListTrainSamples, taste APIs
HTTP AssistentChat → knowledge: {catalog, hops, results}; legacy civitai_results shim
Persona UI «Знания»: attach toggles; bundled personas default attach civitai-krea2 + ru-fictext-rplus
Skill knowledge: list / search / upsert / forget

Default attach (bundled only)

neutral, aggressive, dreamer: civitai-krea2 + ru-fictext-rplus
UI-created personas: no auto-attach
Pack leonid: from assistent-pack.yaml knowledge.attach

Index on VM

On book push or sha change: reindex search.jsonl → sqlite FTS books_fts. Progress in UI on first chat.

1.7 KiB Raw Permalink Blame History